Nano Banana 2: High-Speed Image Generation Model with Pro-Level Capabilities
Key Points
- Combines Pro-level capabilities with Flash speed for rapid image generation
- Supports up to 4K resolution with subject consistency across multiple characters
- Rolling out across Google products including Gemini, Search, and Ads
Summary
Google DeepMind has released Nano Banana 2 (Gemini 3.1 Flash Image), a new state-of-the-art image generation model that combines the advanced capabilities of Nano Banana Pro with the lightning-fast speed of Gemini Flash. The model enables rapid image generation and editing while maintaining high visual quality and production-ready specifications.
Key Features
- Advanced World Knowledge: Leverages Gemini's real-world knowledge base with real-time web search integration for accurate subject rendering
- Precision Text Rendering: Generates accurate, legible text with translation and localization capabilities within images
- Subject Consistency: Maintains character resemblance for up to 5 characters and fidelity of up to 14 objects in single workflow
- Production-Ready Specs: Supports various aspect ratios and resolutions from 512px to 4K
- Enhanced Visual Fidelity: Delivers vibrant lighting, richer textures, and sharper details at Flash speed
Availability
- Gemini App: Replaces Nano Banana Pro across Fast, Thinking, and Pro models
- Google Search: Available in AI Mode and Lens across 141 countries and 8 additional languages
- AI Studio + API: Available in preview with Gemini API
- Google Cloud: Available in preview with Vertex AI
- Google Ads: Powers campaign creation suggestions
- Flow: New default image generation model for all users
AI Content Identification
Google continues improving SynthID technology with C2PA Content Credentials integration, providing enhanced provenance tracking for AI-generated content. SynthID verification has been used over 20 million times since November launch.